qazal
b10802eb53
use existing VIZ ContextVar instead of getenv ( #14610 )
2026-02-08 15:37:55 +09:00
chenyu
510b65489e
style change rangeify assign [pr] ( #14616 )
...
consistent naming, also a standalone fucntion to replace complicated lambda
2026-02-07 15:47:32 -05:00
chenyu
b7afd4471c
use arg instead of 3rd op for ASSIGN [pr] ( #14613 )
2026-02-07 14:17:10 -05:00
nimlgen
88c3022223
amd: kfd iface early exit ( #14612 )
...
* amd: kfd iface early exit
* l
* revert
2026-02-07 18:57:10 +03:00
nimlgen
ce7bfc6ce8
nv: use nv_flags for all fields ( #14607 )
2026-02-07 15:01:38 +03:00
qazal
c2544e2252
viz: remove outdated comment ( #14608 )
2026-02-07 20:05:24 +09:00
nimlgen
6838b35cff
mockgpu: hevc ( #14606 )
...
* mockgpu: hevc
* eng
2026-02-07 12:27:55 +03:00
chenyu
884592f6c8
pin z3-solver version ( #14605 )
...
found exact input that crashes z3 4.15.4
2026-02-06 22:49:31 -05:00
George Hotz
7a2a3b5c71
Remove Ops.KERNEL, it's all Ops.CALL now ( #14603 )
2026-02-07 10:21:54 +08:00
George Hotz
ca6604eae2
kernel is call ( #14577 )
...
* call is kernel
* closer
* fix bugs
* dedup
* pm_gate_kernel_sink
* better
* Revert "better"
This reverts commit b4c799b810e53f094ce7
2026-02-07 10:10:14 +08:00
wozeparrot
d87ae1c84c
feat: tinyfs load test in benchmark ( #14602 )
2026-02-06 18:00:00 -08:00
ttomsa
462b455562
cleanup linearize ( #14523 )
2026-02-07 08:54:02 +08:00
ttomsa
d5652e4da2
new dtype aliases ( #14596 )
2026-02-07 08:53:35 +08:00
Christopher Milan
ad9e2f0de7
decompose bf16 ( #14601 )
2026-02-06 19:24:09 -05:00
Christopher Milan
7bb45e7df0
decompose fp8 to bigger floats [skip_process_replay] ( #14554 )
...
* decompose fp8 also
* it works
* cleanup
* no shift required
* default to float
* cleanup
* fixes
* fp8e5m2
* don't rely on behavior comparing nans
* cleanup
2026-02-06 19:05:40 -05:00
chenyu
81f6cdb4ab
delete realize_assign [pr] ( #14575 )
...
use realize and realize_srcs like COPY and STORE. src[0] always has BUFFER for base
2026-02-06 17:12:33 -05:00
chenyu
7d193a6e26
fix wgsl bitcast ( #14600 )
...
was wrong for signed int
2026-02-06 16:57:36 -05:00
chenyu
b9fe8b7591
fix opt in process replay [pr] ( #14599 )
2026-02-06 16:49:56 -05:00
chenyu
197ebcbbbc
log seed with flush=True in fuzz_symbolic ( #14597 )
...
* log seed with flush=True in fuzz_symbolic
i think z3 can crash. added reading seed from argv to see if we repro later
* fuzz_symbolic_symbolic_div
2026-02-06 15:03:57 -05:00
nimlgen
fbb67a3f95
am_smi: fix after regen ( #14594 )
2026-02-06 20:57:41 +03:00
qazal
a80fb4e641
viz: better ordering of device engines in profiler ( #14590 )
2026-02-06 23:08:09 +09:00
qazal
b7e3fbe07e
llama: add VIZ=-1 to dev_run ( #14583 )
...
* llama: add VIZ=-1 to dev_run
* readme
* cleaner
* add profile.sh script
* better grouping of options
* add other row
* readme edits
* work
2026-02-06 22:59:22 +09:00
nimlgen
fbeb978170
diff devices for sdma ( #14589 )
...
* start
* x
* fix
* sdma
* c
* clean
* x
* hm
* cleaer
2026-02-06 16:39:12 +03:00
George Hotz
7cb996e153
bottom up earliest rewrites ( #14587 )
...
* better
* bottom up earliest rewrites
* fix
2026-02-06 18:13:07 +08:00
George Hotz
03af2404e2
small changes and test fixes from kernel is call ( #14586 )
2026-02-06 17:08:33 +08:00
George Hotz
3c26ce29b2
make disk tensor tests process safe ( #14584 )
2026-02-06 15:39:55 +08:00
qazal
cf73d7e2a7
hotfix: disable slower asm gemm shape from llama seqlen 8192 ( #14582 )
2026-02-06 15:05:19 +09:00
qazal
be77873974
llama: contig backward for wk / wv matmul backward ( #14581 )
2026-02-06 14:54:00 +09:00
chenyu
15d3344d9e
use int inputs in test_assign ( #14580 )
...
int is less flaky
2026-02-06 00:07:31 -05:00
qazal
50a166a5fa
viz: cleanup amdgpu target mapping ( #14579 )
...
* viz: cleanup amdgpu target mapping
* linter
* unwraps
2026-02-06 13:51:51 +09:00
chenyu
b09dc646f5
revert some late_buffer_view change ( #14578 )
...
revert #14478 which breaks tinyfs
2026-02-05 22:51:40 -05:00
chenyu
d41836f135
remove KERNEL special case in realize_assign [pr] ( #14573 )
2026-02-05 21:55:44 -05:00
George Hotz
6cbcf98627
KernelInfo is required on get_program ( #14571 )
...
* rangeify always adds KernelInfo
* fix tests
* skip flaky test
2026-02-06 10:49:27 +08:00
George Hotz
28c56a783c
add CallInfo and viz call toggle ( #14570 )
2026-02-06 09:30:58 +08:00
wozeparrot
f73468d516
fa: block skipping for fa kv bwd ( #14569 )
2026-02-05 16:13:53 -08:00
chenyu
b7ef775677
more cleanup in create_schedule [pr] ( #14566 )
...
fixed wrong comments and simplified queue building
2026-02-05 16:12:17 -05:00
Garret Castro
cee7ef7ab2
disable threads ( #14555 )
2026-02-05 16:11:32 -05:00
chenyu
79b7799dba
clean up linearize schedule [pr] ( #14565 )
...
* clean up linearize schedule [pr]
don't mix ScheduleItem and UOp in schedule queue
* ok
2026-02-05 15:24:09 -05:00
chenyu
41a179f542
fix test_xlm_roberta_large ( #14564 )
...
onnxruntime does not allow symlink that's outside model dir. update snapshot_download to use local_dir instead of cache_dir. some ad hoc migration step to copy the existing model too
2026-02-05 14:56:06 -05:00
Christopher Milan
aa9dc50577
dtype decomps don't require bitshifts ( #14542 )
...
* dtype decomps don't require bitshifts
* simplify shr/shl
* ruff
2026-02-05 14:42:30 -05:00
Christopher Milan
b47397ab17
list ml_dtypes as dependency for DSP ( #14562 )
...
* pin onnxruntime to 1.23.2 for DSP
* list ml_dtypes instead
This reverts commit 84bb2cc0fc
2026-02-05 14:27:50 -05:00
chenyu
2b47a9a1b5
skip test_xlm_roberta_large ( #14563 )
...
symlink model not allowed in latest onnxruntime
2026-02-05 14:00:24 -05:00
chenyu
42c18da88a
add Ops asserts in toposort sched_sink [pr] ( #14561 )
...
more explicit
2026-02-05 12:40:02 -05:00
nimlgen
483bba4f05
nv: use prof_exec_counter ( #14559 )
2026-02-05 19:00:14 +03:00
qazal
190042358f
llama: faster bf16 matmul / rope backward ( #14558 )
2026-02-05 23:57:25 +09:00
George Hotz
b398335f62
assembly/amd: fix saturation in python remu ( #14557 )
...
* PYTHONREMU: failing test for V_SUB_NC_U32_E64 clamp
* fix saturation in PYTHON_REMU
* simpler
* more tests, less lines
---------
Co-authored-by: Christopher Milan <chrismilan@ucla.edu >
2026-02-05 18:35:57 +08:00
wozeparrot
c1ea6687e5
fa: simpler is faster ( #14548 )
2026-02-05 01:13:17 -08:00
George Hotz
43e7eda4e7
grad_b uses custom gemm ( #14550 )
...
* grad_b uses custom gemm
* fix multi backward, acc is in float32
* test_gemm_batched
* square gemm
---------
Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com >
Co-authored-by: qazal <qazal.software@gmail.com >
2026-02-05 15:22:27 +09:00
qazal
f9cfb64cd9
test asm_gemm in CI ( #14551 )
...
* test asm_gemm in CI
* default float16
* use a smaller shape for multi
* smaller size
* smaller for CI
* smaller for ci
* need half
2026-02-05 13:32:22 +09:00
chenyu
c0ca7f9c51
use more UOp.sum and UOp.prod [pr] ( #14549 )
2026-02-04 22:05:20 -05:00
